Dissertation/ Thesis
Προβολή σε EDS

Representation Learning for CRISPR-Cas13d Efficacy and Single-Cell RNA Sequencing Data

Λεπτομέρειες βιβλιογραφικής εγγραφής
Τίτλος: Representation Learning for CRISPR-Cas13d Efficacy and Single-Cell RNA Sequencing Data
Συγγραφείς: Stirn, Andrew
Έτος έκδοσης: 2025
Συλλογή: Columbia University: Academic Commons
Θεματικοί όροι: Artificial intelligence, Machine learning, Nucleotide sequence--Computer programs, RNA, CRISPR (Genetics), Genomics
Περιγραφή: This thesis develops multiple novel methods spanning computational genomics and machine learning. CRISPR-Cas13d is a programmable RNA-targeting system that can knockdown specific RNA transcripts. Our method, TIGER (Wessels et al., 2023), is the first tool to model CRISPR-Cas13d efficacy as a function of both the target RNA and the guide RNA (gRNA) sequences; doing so enables biologists using our model to design the most effective gRNA for a target transcript, check a gRNA library for any unintended off-target effects, and engineer mismatches between a gRNA and its target to titrate CRISPR-Cas13d efficacy. We leverage TIGER to study CRISPR-Cas13d binding affinity at junction splice sites (Megan D Schertzer et al., 2023) finding CRISPR-Cas13d can uniquely target 89% of human isoforms with high efficacy. Thereafter, we develop two methods (Stirn & Knowles, 2020; Stirn et al., 2023) for generating well-calibrated heteroscedastic variance estimates, which we integrate into TIGER to study sequence-based heteroscedasticity in CRISPR-Cas13d. The goal of single-cell RNA sequencing (scRNA-seq) integration is to isolate technical variation from the biological signals of interest. Several popular integration methods use a semi-supervised variational autoencoding (VAE) framework (Kingma et al., 2014) with partially observed cell-type labels to learn a low-dimensional representation disentangled from technical effects. To better handle partially observed labels in the amortized variational setting, we develop a new distribution on the simplex (Stirn et al., 2019) that mimics the Dirichlet distribution but has analytic reparameterization gradients and thus low gradient variance. Additionally, we develop a novel method for learning structured latent embeddings for the VAE (Kingma & Welling, 2014) that outperforms existing clustering methods on benchmark datasets and state-of-the-art scRNA-seq integration methods when combined with scVI (Lopez et al., 2018), a popular VAE-based scRNA-seq integration method. Our final ...
Τύπος εγγράφου: thesis
Γλώσσα: English
DOI: 10.7916/c1gh-7403
Διαθεσιμότητα: https://doi.org/10.7916/c1gh-7403
Αριθμός Καταχώρησης: edsbas.F186332E
Βάση Δεδομένων: BASE
FullText Text:
  Availability: 0
CustomLinks:
  – Url: https://doi.org/10.7916/c1gh-7403#
    Name: EDS - BASE (ns324271)
    Category: fullText
    Text: View record from BASE
Header DbId: edsbas
DbLabel: BASE
An: edsbas.F186332E
RelevancyScore: 892
AccessLevel: 3
PubType: Dissertation/ Thesis
PubTypeId: dissertation
PreciseRelevancyScore: 891.935607910156
IllustrationInfo
Items – Name: Title
  Label: Title
  Group: Ti
  Data: Representation Learning for CRISPR-Cas13d Efficacy and Single-Cell RNA Sequencing Data
– Name: Author
  Label: Authors
  Group: Au
  Data: <searchLink fieldCode="AR" term="%22Stirn%2C+Andrew%22">Stirn, Andrew</searchLink>
– Name: DatePubCY
  Label: Publication Year
  Group: Date
  Data: 2025
– Name: Subset
  Label: Collection
  Group: HoldingsInfo
  Data: Columbia University: Academic Commons
– Name: Subject
  Label: Subject Terms
  Group: Su
  Data: <searchLink fieldCode="DE" term="%22Artificial+intelligence%22">Artificial intelligence</searchLink><br /><searchLink fieldCode="DE" term="%22Machine+learning%22">Machine learning</searchLink><br /><searchLink fieldCode="DE" term="%22Nucleotide+sequence--Computer+programs%22">Nucleotide sequence--Computer programs</searchLink><br /><searchLink fieldCode="DE" term="%22RNA%22">RNA</searchLink><br /><searchLink fieldCode="DE" term="%22CRISPR+%28Genetics%29%22">CRISPR (Genetics)</searchLink><br /><searchLink fieldCode="DE" term="%22Genomics%22">Genomics</searchLink>
– Name: Abstract
  Label: Description
  Group: Ab
  Data: This thesis develops multiple novel methods spanning computational genomics and machine learning. CRISPR-Cas13d is a programmable RNA-targeting system that can knockdown specific RNA transcripts. Our method, TIGER (Wessels et al., 2023), is the first tool to model CRISPR-Cas13d efficacy as a function of both the target RNA and the guide RNA (gRNA) sequences; doing so enables biologists using our model to design the most effective gRNA for a target transcript, check a gRNA library for any unintended off-target effects, and engineer mismatches between a gRNA and its target to titrate CRISPR-Cas13d efficacy. We leverage TIGER to study CRISPR-Cas13d binding affinity at junction splice sites (Megan D Schertzer et al., 2023) finding CRISPR-Cas13d can uniquely target 89% of human isoforms with high efficacy. Thereafter, we develop two methods (Stirn & Knowles, 2020; Stirn et al., 2023) for generating well-calibrated heteroscedastic variance estimates, which we integrate into TIGER to study sequence-based heteroscedasticity in CRISPR-Cas13d. The goal of single-cell RNA sequencing (scRNA-seq) integration is to isolate technical variation from the biological signals of interest. Several popular integration methods use a semi-supervised variational autoencoding (VAE) framework (Kingma et al., 2014) with partially observed cell-type labels to learn a low-dimensional representation disentangled from technical effects. To better handle partially observed labels in the amortized variational setting, we develop a new distribution on the simplex (Stirn et al., 2019) that mimics the Dirichlet distribution but has analytic reparameterization gradients and thus low gradient variance. Additionally, we develop a novel method for learning structured latent embeddings for the VAE (Kingma & Welling, 2014) that outperforms existing clustering methods on benchmark datasets and state-of-the-art scRNA-seq integration methods when combined with scVI (Lopez et al., 2018), a popular VAE-based scRNA-seq integration method. Our final ...
– Name: TypeDocument
  Label: Document Type
  Group: TypDoc
  Data: thesis
– Name: Language
  Label: Language
  Group: Lang
  Data: English
– Name: DOI
  Label: DOI
  Group: ID
  Data: 10.7916/c1gh-7403
– Name: URL
  Label: Availability
  Group: URL
  Data: https://doi.org/10.7916/c1gh-7403
– Name: AN
  Label: Accession Number
  Group: ID
  Data: edsbas.F186332E
PLink https://search.ebscohost.com/login.aspx?direct=true&site=eds-live&db=edsbas&AN=edsbas.F186332E
RecordInfo BibRecord:
  BibEntity:
    Identifiers:
      – Type: doi
        Value: 10.7916/c1gh-7403
    Languages:
      – Text: English
    Subjects:
      – SubjectFull: Artificial intelligence
        Type: general
      – SubjectFull: Machine learning
        Type: general
      – SubjectFull: Nucleotide sequence--Computer programs
        Type: general
      – SubjectFull: RNA
        Type: general
      – SubjectFull: CRISPR (Genetics)
        Type: general
      – SubjectFull: Genomics
        Type: general
    Titles:
      – TitleFull: Representation Learning for CRISPR-Cas13d Efficacy and Single-Cell RNA Sequencing Data
        Type: main
  BibRelationships:
    HasContributorRelationships:
      – PersonEntity:
          Name:
            NameFull: Stirn, Andrew
    IsPartOfRelationships:
      – BibEntity:
          Dates:
            – D: 01
              M: 01
              Type: published
              Y: 2025
          Identifiers:
            – Type: issn-locals
              Value: edsbas
            – Type: issn-locals
              Value: edsbas.oa
ResultId 1